Study and Implementation of Morphology for Image Segmentation

Abstract

The field of computer vision is concerned with extracting features and information from images in order to make analysis of images easier so that more and more information can be extracted. The task of image segmentation is a first step in many computer vision methods and serves to simplify the problem by grouping the pixels having similar attributes in the image. It is hard to clearly define image segmentation because there are many levels of detail in an image and therefore many possible ways of meaningfully grouping pixels i.e., various methods of image segmentation exist utilizing different image characteristics, e.g. shape, texture, motion, contrast, gray level etc. This thesis, presents a way to approach image segmentation of ultrasound images as well segmentation followed by counting of objects in images by using mathematical morphology, explain an efficient implementation for this approach, and show segmentation results using mathematical morphology.